{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AXLK4TV7ZXMYMC6QVDXDMHMHYL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8a627d0c06f34f296724eabec935eed6a9ee94c5a67d5ed4f593716ad45f1cbf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:59:58Z","title_canon_sha256":"bfd7d3c21260b5f0783aa90e639a849aed3e5f6737b23a8c0f5e3e726553d2ac"},"schema_version":"1.0","source":{"id":"2501.05453","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05453","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05453v1","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05453","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"AXLK4TV7ZXMY","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"AXLK4TV7ZXMYMC6Q","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"AXLK4TV7","created_at":"2026-07-05T09:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:3c505ef5468e8c5c3baf761bb04dd797e7637339e597dc72b489b7ce024eea35","target":"graph","created_at":"2026-07-05T09:59:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.05453/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We empirically study autoregressive pre-training from videos. To perform our study, we construct a series of autoregressive video models, called Toto. We treat videos as sequences of visual tokens and train transformer models to autoregressively predict future tokens. Our models are pre-trained on a diverse dataset of videos and images comprising over 1 trillion visual tokens. We explore different architectural, training, and inference design choices. We evaluate the learned visual representations on a range of downstream tasks including image recognition, video classification, object tracking","authors_text":"Christoph Feichtenhofer, Ilija Radosavovic, Jathushan Rajasegaran, Jitendra Malik, Rahul Ravishankar, Yossi Gandelsman","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:59:58Z","title":"An Empirical Study of Autoregressive Pre-training from Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05453","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e7c2901b8b9c88757c89ba562253becf7d69ae9a70a8030d16d8b3c261f820be","target":"record","created_at":"2026-07-05T09:59:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8a627d0c06f34f296724eabec935eed6a9ee94c5a67d5ed4f593716ad45f1cbf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:59:58Z","title_canon_sha256":"bfd7d3c21260b5f0783aa90e639a849aed3e5f6737b23a8c0f5e3e726553d2ac"},"schema_version":"1.0","source":{"id":"2501.05453","kind":"arxiv","version":1}},"canonical_sha256":"05d6ae4ebfcdd9860bd0a8ee361d87c2c67e7503a7ff350d5e7fc942c02fd697","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05d6ae4ebfcdd9860bd0a8ee361d87c2c67e7503a7ff350d5e7fc942c02fd697","first_computed_at":"2026-07-05T09:59:10.118499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:10.118499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zhBKLkod5ldRJuWVNB5yhiOBfYxae9vGG/Jtc7Pun9o96js32/7CCNjXHjM252BmVyfVlvyabfvreXE/xpELBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:10.118980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05453","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7c2901b8b9c88757c89ba562253becf7d69ae9a70a8030d16d8b3c261f820be","sha256:3c505ef5468e8c5c3baf761bb04dd797e7637339e597dc72b489b7ce024eea35"],"state_sha256":"0f2712f5f3a9939dffdf8996ac8dbd4e426b49bb813c63dd6f21e9e7f99775c0"}